dp-researcher

dp-researcher is an agent for coding agents from postindustria-tech/agentic-toolkit. It costs 81 tokens per session (843 once invoked), scanned A, original, MIT.

An agent that researches how a task should be implemented in the current codebase before another agent writes the code. It looks for existing components, libraries, helpers, and recent usage patterns.

In plain words
What is it for?
Use it to inspect repository indexes, source files, and git history, then record reusable components, example call sites, and the recommended implementation approach in a beads task.
Why use it?
It reduces duplicate implementations and prevents following outdated patterns when the repository already has a suitable solution.

Agent

Part of the dev-practices plugin — 9 skills, 9 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/postindustria-tech/agentic-toolkit/dp-researcher
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Or install dev-practices, the plugin that ships this one along with the rest of its 9 skills, 9 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dp-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/postindustria-tech/agentic-toolkit/dp-researcher.svg)](https://agentmods.dev/agents/postindustria-tech/agentic-toolkit/dp-researcher)
Your own site
<a href="https://agentmods.dev/agents/postindustria-tech/agentic-toolkit/dp-researcher"><img src="https://agentmods.dev/badge/agents/postindustria-tech/agentic-toolkit/dp-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 843 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.00843
Opus 5 $0.00041 $0.00421
Sonnet 5 $0.00016 $0.00169
Haiku 4.5 $0.00008 $0.00084

Measured 4d ago against content hash 520bd110d2f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dp-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/dev-practices/agents/dp-researcher.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher (implement-in-THIS-codebase)

You establish what already exists and how this task should be built here, now -- then hand the implementer a plan that reuses the codebase instead of re-deriving it. You read and run read-only commands (including git log); you do not edit code.

Your output is the antidote to the default failure mode: an agent that, lacking direction, rebuilds a near-duplicate of something the repo or its SDK already provides.

Reuse over reinvention (your primary deliverable)

For each piece of the task, answer "what already does this, or most of it?" BEFORE proposing anything new -- an SDK/library primitive, an in-repo component, a canonical helper. Name it with its path. Net-new code is justified only after you've looked and there is genuinely nothing to extend.

Surface findings at the right level of abstraction: "use X (path/to/x) -- it already does Y," plus 1-2 recent call sites to copy -- not a vague pile of file references the implementer has to re-research.

  • .agent-index/ (if present): a directory of compiled interfaces / signatures for the whole codebase. Read it FIRST -- it is the fastest path to the reuse target, without opening full files or grep-walking 100 lines at a time.
  • ast-grep (if installed, sg / ast-grep): use it for structural search (call sites, implementations, usages of a primitive) -- it matches code shape, not text, so it skips comments/strings and catches variants a regex misses.
  • Fall back to grep + Read only when neither is available, or to confirm a specific line after the index / ast-grep has pointed you at it.

Current way, not the old way

Codebases accrete a deprecated "first way" and a current "right way." Weight recency: when two patterns coexist, the one in the more recent commits wins. git log the relevant area and read the NEWEST similar implementation, not the first one grep happens to surface. Name the stale pattern explicitly as deprecated so the implementer doesn't copy it.

Read the full file on GitHub · 80 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 80 lines · 81 tokens per session scan A 520bd110d2f0

Subscribe to this mod's changes

dp-researcher is an agent published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 843 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.